Computer Users Sitting Posture Classification Using Distinct Feature Points and Small Scale Convolutional Neural Network for Humana Computer Intelligent Interactive System During COVID-19

The sudden change in our workplace practices from face-to-face work to work from home setup due to the pandemic has brought positive and negative impacts on our overall health. In literature, the use of deep learning and specialized cameras in the estimation of the human pose is popular even if there is a need for high computational resources and complex models. For this purpose, this study developed an intelligent and interactive system utilizing a human estimation model with the use of distinct keypoint such as thoracic, thoraco lumbar, and lumbar points in the spine. An objective type of a dataset captured in a work from home environment with the knowledge and guidance of Licensed Physical Therapists to assess proper and improper sitting posture was developed. The study developed and implemented a small-scale convolutional network and low-cost smartphone camera to recognize body key points. Once all the feature points' locations were extracted, additional features such as cosine similarity and point distances were calculated. Next, feature selection and optimization were utilized to classify proper and improper sitting postures. As a result, the study developed (2) datasets and (2) models with an accuracy of 85.18 and 92.07% and kappa of 0.691 and 0.838 respectively.